ooxx问题

平头哥爱python

1. 
   
2. import urllib.request
   
3. import os
   
4. 
   
5. def url_open(url):
   
6.     req = urllib.request.Request(url)
   
7.     req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36')
   
8.     response = urllib.request.urlopen(url)
   
9. 
   
10.     html = response.read()
    
11.     return html
    
12. 
    
13. def getpage(url):
    
14.     # req = urllib.request.Request(url)
    
15.     # req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36')
    
16.     # response = urllib.request.urlopen(req)
    
17.     html = url_open(url).decode('utf-8')
    
18. 
    
19.     a = html.find('current-comment-page') + 23
    
20.     b = html.find(']', a)
    
21.     print(url)
    
22.     return html[a:b]
    
23. 
    
24. def findimg(url):
    
25.     html = url_open(url).decode('utf-8')
    
26.     imgaddress = []
    
27.     a = html.find('img src=')
    
28.     while a != -1:
    
29.         b = html.find('.jpg', a, a+255)
    
30.         if b != -1:
    
31.             imgaddress.append(html[a+9:b+4])
    
32.         else:
    
33.             b = a + 9
    
34.         a = html.find('img src=', b)
    
35.     for each in imgaddress:
    
36.         print(each)
    
37. 
    
38. 
    
39. def saveimg(folder, imgaddress):
    
40.     for each in imgaddress:
    
41.         # each = 'http://' + each
    
42.         filename = each.split('/')[-1]
    
43.         with open(filename, 'wb') as f:
    
44.             img = url_open(each)
    
45.             f.write(img)
    
46. 
    
47. def downloadmm(folder='picture', pages=10):
    
48.     os.mkdir(folder)
    
49.     os.chdir(folder)
    
50. 
    
51.     url = 'http://jandan.net/ooxx/'
    
52.     pagenum = int(getpage(url))
    
53. 
    
54.     for i in range(pages):
    
55.         pagenum -= i
    
56.         pageurl = url + 'page-' + str(pagenum) + '#comments'
    
57.         imgaddress = findimg(pageurl)
    
58.         saveimg(folder, imgaddress)
    
59. 
    
60. 
    
61. if __name__ == '__main__':
    
62.     downloadmm()

复制代码

不能爬取图片，在    for each in imgaddress:这个语句中会出现下面的错误
TypeError: 'NoneType' object is not iterable。
各位大佬知道怎么办嘛

heidern0612

错误都告诉你了，空值无法迭代。

要么就是你没爬着，要么就是服务器给禁了。

一种情况就是代码不是你写的，研究不明白。

一种情况就是自己写的代码，不知道为啥出错。

_谪仙

匹配不到，imgaddress为空值，放在循环里就会爆出该错误